LAB6

library(tidyverse)

## ── Attaching packages ─────────────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.3.2     ✓ purrr   0.3.4
## ✓ tibble  3.0.3     ✓ dplyr   1.0.2
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.3.1     ✓ forcats 0.5.0

## ── Conflicts ────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(maps)

## 
## Attaching package: 'maps'

## The following object is masked from 'package:purrr':
## 
##     map

library(mapdata)
library(lubridate)

## 
## Attaching package: 'lubridate'

## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

library(viridis)

## Loading required package: viridisLite

library(wesanderson)

daily_report <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/04-02-2020.csv")) %>% 
  rename(Long = "Long_") 

## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_character(),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character()
## )

ggplot(daily_report, aes(x = Long, y = Lat, size = Confirmed/1000)) +
    borders("world", colour = NA, fill = "grey90") +
    theme_bw() +
    geom_point(shape = 21, color='purple', fill='purple', alpha = 0.5) +
    labs(title = 'World COVID-19 Confirmed cases',x = '', y = '',
        size="Cases (x1000))") +
    theme(legend.position = "right") +
    coord_fixed(ratio=1.0)

## Warning: Removed 54 rows containing missing values (geom_point).

daily_report <-   read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/04-05-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  filter(Country_Region == "US") %>% 
  filter (!Province_State %in% c("Alaska","Hawaii", "American Samoa",
                  "Puerto Rico","Northern Mariana Islands", 
                  "Virgin Islands", "Recovered", "Guam", "Grand Princess",
                  "District of Columbia", "Diamond Princess")) %>% 
  filter(Lat > 0)

## Parsed with column specification:
## cols(
##   FIPS = col_character(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_datetime(format = ""),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character()
## )

ggplot(daily_report, aes(x = Long, y = Lat, size = Confirmed/1000)) +
    borders("state", colour = "black", fill = "grey90") +
    theme_bw() +
    geom_point(shape = 21, color='purple', fill='purple', alpha = 0.5) +
    labs(title = 'COVID-19 Confirmed Cases in the US', x = '', y = '',
        size="Cases (x1000))") +
    theme(legend.position = "right") +
    coord_fixed(ratio=1.5)

mybreaks <- c(1, 100, 1000, 10000, 10000)
ggplot(daily_report, aes(x = Long, y = Lat, size = Confirmed)) +
    borders("state", colour = "white", fill = "grey90") +
    geom_point(aes(x=Long, y=Lat, size=Confirmed, color=Confirmed),stroke=F, alpha=0.7) +
    scale_size_continuous(name="Cases", trans="log", range=c(1,7), 
                        breaks=mybreaks, labels = c("1-99",
                        "100-999", "1,000-9,999", "10,000-99,999", "50,000+")) +
    scale_color_viridis_c(option="viridis",name="Cases",
                        trans="log", breaks=mybreaks, labels = c("1-99",
                        "100-999", "1,000-9,999", "10,000-99,999", "50,000+"))  +
# Cleaning up the graph
  ##BORDERS DEFINE THE GRAPHS
  
  theme_void() + 
    guides( colour = guide_legend()) +
    labs(title = "Anisa Dhana's lagout for COVID-19 Confirmed Cases in the US'") +
    theme(
      legend.position = "bottom",
      text = element_text(color = "#22211d"),
      plot.background = element_rect(fill = "#ffffff", color = NA), 
      panel.background = element_rect(fill = "#ffffff", color = NA), 
      legend.background = element_rect(fill = "#ffffff", color = NA)
    ) +
    coord_fixed(ratio=1.5)

## Warning: Transformation introduced infinite values in discrete y-axis

## Warning: Transformation introduced infinite values in discrete y-axis

## Warning in sqrt(x): NaNs produced

## Warning: Removed 40 rows containing missing values (geom_point).

##MAPPING DATA TO SHAPES

daily_report <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/04-02-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  filter(Country_Region == "US") %>% 
  group_by(Province_State) %>% 
  summarize(Confirmed = sum(Confirmed)) %>% 
  mutate(Province_State = tolower(Province_State))

## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_character(),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character()
## )

## `summarise()` ungrouping output (override with `.groups` argument)

# load the US map data
us <- map_data("state")
# We need to join the us map data with our daily report to make one data frame/tibble
state_join <- left_join(us, daily_report, by = c("region" = "Province_State"))
# plot state map

##USING R COLOR PALETTES

##integrating the wes anderson color palette

ggplot(data = us, mapping = aes(x = long, y = lat, group = group)) + 
  coord_fixed(1.5) + 
# Add data layer
  geom_polygon(data = state_join, aes(fill = Confirmed), color = "black") +
  scale_fill_gradientn(colours = 
                         wes_palette("Zissou1", 100, type = "continuous"),
                         trans = "log10") +
  labs(title = "COVID-19 Confirmed Cases in the US'")

##RCOLOR BREWER

##USE FOR #3!!!!

library(RColorBrewer)
# To display only colorblind-friendly brewer palettes, specify the option colorblindFriendly = TRUE as follow:
# display.brewer.all(colorblindFriendly = TRUE)
# Get and format the covid report data
report_03_27_2020 <-   read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/04-02-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  unite(Key, Admin2, Province_State, sep = ".") %>% 
  group_by(Key) %>% 
  summarize(Confirmed = sum(Confirmed)) %>% 
  mutate(Key = tolower(Key))

## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_character(),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character()
## )

## `summarise()` ungrouping output (override with `.groups` argument)

# dim(report_03_27_2020)
# get and format the map data
us <- map_data("state")
counties <- map_data("county") %>% 
  unite(Key, subregion, region, sep = ".", remove = FALSE)
# Join the 2 tibbles
state_join <- left_join(counties, report_03_27_2020, by = c("Key"))
# sum(is.na(state_join$Confirmed))
ggplot(data = us, mapping = aes(x = long, y = lat, group = group)) + 
  coord_fixed(1.3) + 
  # Add data layer
  borders("state", colour = "black") +
  geom_polygon(data = state_join, aes(fill = Confirmed)) +
  scale_fill_gradientn(colors = brewer.pal(n = 5, name = "PuRd"),
                       breaks = c(1, 10, 100, 1000, 10000, 100000),
                       trans = "log10", na.value = "White") +
  ggtitle("Number of Confirmed Cases by US County") +
  theme_bw() 

## Warning: Transformation introduced infinite values in discrete y-axis

##now looking just at the state of MA…

daily_report <-   read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/04-02-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  filter(Province_State == "Massachusetts") %>% 
  group_by(Admin2) %>% 
  summarize(Confirmed = sum(Confirmed)) %>% 
  mutate(Admin2 = tolower(Admin2))

## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_character(),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character()
## )

## `summarise()` ungrouping output (override with `.groups` argument)

us <- map_data("state")
ma_us <- subset(us, region == "massachusetts")
counties <- map_data("county")
ma_county <- subset(counties, region == "massachusetts")
state_join <- left_join(ma_county, daily_report, by = c("subregion" = "Admin2")) 
# plot state map
ggplot(data = ma_county, mapping = aes(x = long, y = lat, group = group)) + 
  coord_fixed(1.3) + 
# Add data layer
  geom_polygon(data = state_join, aes(fill = Confirmed), color = "white") +
    scale_fill_gradientn(colors = brewer.pal(n = 5, name = "BuGn"),
                         trans = "log10") +
  labs(title = "COVID-19 Confirmed Cases in Massachusetts'")

daily_report

## # A tibble: 14 x 2
##    Admin2              Confirmed
##    <chr>                   <dbl>
##  1 barnstable                283
##  2 berkshire                 213
##  3 bristol                   424
##  4 dukes and nantucket        12
##  5 essex                    1039
##  6 franklin                   85
##  7 hampden                   546
##  8 hampshire                 102
##  9 middlesex                1870
## 10 norfolk                   938
## 11 plymouth                  621
## 12 suffolk                  1896
## 13 unassigned                270
## 14 worcester                 667

##interactive graph making! Can do this by using ‘plotly’

library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

ggplotly(
  ggplot(data = ma_county, mapping = aes(x = long, y = lat, group = group)) + 
  coord_fixed(1.3) + 
# Add data layer
  geom_polygon(data = state_join, aes(fill = Confirmed), color = "black") +
    scale_fill_gradientn(colours = 
                         wes_palette("Zissou1", 100, type = "continuous")) +
  ggtitle("COVID-19 Cases in MA") +
# Cleaning up the graph
  labs(x=NULL, y=NULL) +
  theme(panel.border = element_blank()) +
  theme(panel.background = element_blank()) +
  theme(axis.ticks = element_blank()) +
  theme(axis.text = element_blank()))

## Warning: `group_by_()` is deprecated as of dplyr 0.7.0.
## Please use `group_by()` instead.
## See vignette('programming') for more help
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_warnings()` to see where this warning was generated.

##EXERCISES

##1.

daily_report <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/09-26-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  group_by(Country_Region, Long, Lat) %>% 
  summarise(Confirmed= sum(Confirmed))

## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_datetime(format = ""),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character(),
##   Incidence_Rate = col_double(),
##   `Case-Fatality_Ratio` = col_double()
## )

## `summarise()` regrouping output by 'Country_Region', 'Long' (override with `.groups` argument)

ggplot(daily_report, aes(x = Long, y = Lat, size = Confirmed/1000)) +
    borders("world", colour = NA, fill = "grey90") +
    theme_bw() +
    geom_point(shape = 21, color='green', fill='green', alpha = 0.5) +
    labs(title = 'World COVID-19 Confirmed cases Country/Region',x = '', y = '',
        size="Cases (x10000))") +
    theme(legend.position = "right") +
    coord_fixed(ratio=0.75)

## Warning: Removed 13 rows containing missing values (geom_point).

##2.

daily_report_9_26_2020 <-   read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/09-26-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  filter(Country_Region == "US") %>% 
  filter (!Province_State %in% c("Alaska","Hawaii", "American Samoa",
                  "Puerto Rico","Northern Mariana Islands", 
                  "Virgin Islands", "Recovered", "Guam", "Grand Princess",
                  "District of Columbia", "Diamond Princess")) %>% 
filter(Lat>0)

## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_datetime(format = ""),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character(),
##   Incidence_Rate = col_double(),
##   `Case-Fatality_Ratio` = col_double()
## )

mybreaks <- c(1, 100, 1000, 10000, 10000)
ggplot(daily_report_9_26_2020, aes(x = Long, y = Lat, size = Confirmed)) +
    borders("state", colour = "white", fill = "grey90") +
    geom_point(aes(x=Long, y=Lat, size=Confirmed, color=Confirmed),stroke=F, alpha=0.8, size = 1.5) +
    scale_size_continuous(name="Cases", trans="log", range=c(1,7), 
        breaks=mybreaks, labels = c("1-99",
                    "100-999", "1,000-9,999", "10,000-99,999", "50,000+")) +
    scale_color_viridis_c(option="viridis",name="Cases",
                        trans="log", breaks=mybreaks, labels = c("1-99",
                        "100-999", "1,000-9,999", "10,000-99,999", "50,000+"))  +
# Cleaning up the graph
  
  theme_void() + 
    guides( colour = guide_legend()) +
    labs(title = "Anisa Dhana's lagout for COVID-19 Confirmed Cases in the US'") +
    theme(
      legend.position = "bottom",
      text = element_text(color = "#22211d"),
      plot.background = element_rect(fill = "#ffffff", color = NA), 
      panel.background = element_rect(fill = "#ffffff", color = NA), 
      legend.background = element_rect(fill = "#ffffff", color = NA)
    ) +
    coord_fixed(ratio=1.3)

## Warning: Transformation introduced infinite values in discrete y-axis

##3.

report_09_26_2020 <-   read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/09-26-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  unite(Key, Admin2, Province_State, sep = ".") %>% 
  group_by(Key) %>% 
  summarize(Confirmed = sum(Confirmed)) %>% 
  mutate(Key = tolower(Key))

## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_datetime(format = ""),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character(),
##   Incidence_Rate = col_double(),
##   `Case-Fatality_Ratio` = col_double()
## )

## `summarise()` ungrouping output (override with `.groups` argument)

us <- map_data("state")
counties <- map_data("county") %>% 
  unite(Key, subregion, region, sep = ".", remove = FALSE)

state_join <- left_join(counties, report_09_26_2020, by = c("Key"))

ggplot(data = us, mapping = aes(x = long, y = lat, group = group)) + 
  coord_fixed(1.3) + 
 
  borders("state", colour = "black") +
  geom_polygon(data = state_join, aes(fill = Confirmed)) +
  scale_fill_gradientn(colors = brewer.pal(n = 5, name = "Greens"),
                       breaks = c(1, 10, 100, 1000, 10000, 100000),
                       trans = "log10", na.value = "White") +
  ggtitle("Number of Confirmed Cases by US County") +
  theme_bw() 

## Warning: Transformation introduced infinite values in discrete y-axis

##4.

daily_report_ca <-   read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/09-26-2020.csv")) %>% 
  rename(Long = "Long_") %>% 
  filter(Province_State == "California") %>% 
  group_by(Admin2) %>% 
  summarize(Confirmed = sum(Confirmed)) %>% 
  mutate(Admin2 = tolower(Admin2))

## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_datetime(format = ""),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character(),
##   Incidence_Rate = col_double(),
##   `Case-Fatality_Ratio` = col_double()
## )

## `summarise()` ungrouping output (override with `.groups` argument)

us <- map_data("state")
ca_us <- subset(us, region == "california")
counties <- map_data("county")
ca_county <- subset(counties, region == "california")
state_join_ca <- left_join(ca_county, daily_report_ca, by = c("subregion" = "Admin2")) 
# plot state map
ggplot(data = ca_county, mapping = aes(x = long, y = lat, group = group)) + 
  coord_fixed(1.3) + 
# Add data layer
  geom_polygon(data = state_join_ca, aes(fill = Confirmed), color = "white") +
    scale_fill_gradientn(colors = brewer.pal(n = 5, name = "Greens"),
                         trans = "log10") +
  labs(title = "COVID-19 Confirmed Cases in California'")

ggplotly(
  ggplot(data = ca_county, mapping = aes(x = long, y = lat, group = group)) + 
  coord_fixed(1.3) + 
  geom_polygon(data = state_join_ca, aes(fill = Confirmed), color = "black") +
    scale_fill_gradientn(colours = 
                         brewer.pal(n=5, name = "Paired")) +
  ggtitle("COVID-19 Cases in California") +
  labs(x=NULL, y=NULL) +
  theme(panel.border = element_blank()) +
  theme(panel.background = element_blank()) +
  theme(axis.ticks = element_blank()) +
  theme(axis.text = element_blank())
)

##5. Create a report with static maps and interactive graphs that is meant to be read by others (e.g. your friends and family). Hide warnings, messages and even the code you used so that it is readable. Included references. Link to the Lab 6 report from your Github site. Submit the link to Moodle. Hide warnings, messages and even the code you used so that it is readable. Included references. Link to the Lab 6 report from your Github site. Submit the link to Moodle. I will talk more about the format on Wed.

## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_character(),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character()
## )

## `summarise()` ungrouping output (override with `.groups` argument)

## Parsed with column specification:
## cols(
##   FIPS = col_double(),
##   Admin2 = col_character(),
##   Province_State = col_character(),
##   Country_Region = col_character(),
##   Last_Update = col_datetime(format = ""),
##   Lat = col_double(),
##   Long_ = col_double(),
##   Confirmed = col_double(),
##   Deaths = col_double(),
##   Recovered = col_double(),
##   Active = col_double(),
##   Combined_Key = col_character(),
##   Incidence_Rate = col_double(),
##   `Case-Fatality_Ratio` = col_double()
## )
## `summarise()` ungrouping output (override with `.groups` argument)

R Studio Data Analysis [@RStudio]

#REFERENCES